In the near future, you may be able to make yourself speak in any language, or have video proof of your friend saying he loves to eat poop. It’s all thanks to a new tracking and animation system that can transfer the facial movements of one person into a photorealistic CGI rendering of another person’s face, all in real time. In other words it can make you, or rather an animation of your face, express or say anything.
The jaw-dropping technique was developed by Justus Thies, Michael Zollhöfer, Matthias Nießner, Levi Valgaerts, Marc Stamminger and Christian Theobalt. The group developed custom software that creates parametric models of the source face and the target face with the help of a depth sensor such as the Kinect. Their program also takes into account the real time lighting conditions of the target face to make the resulting animation more realistic.
Before it can work its magic, the system must first analyze the source and target faces so that it can calibrate itself. When that’s done, anything that the source face does will be mimicked in real time by a computer animation that looks just like the target face. Note that the resulting virtual face will still mimic the target’s head movement.
Aside from this “facial reenactment”, the system can also be used to make it so that the virtual face is wearing makeup or different clothing, or is under different lighting conditions.
It’s an insanely useful invention, but obviously it can also be used for nefarious purposes. Now even your face can be hacked. You can download the group’s full paper from Stanford University’s website.
[via Digg]
